centerpoint在KITTI上测试报错

[g1zzy316]

1 error detected in the compilation of "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/ops/centerpoint_postprocess/postprocess.cu".
error: command '/home/lib245/anaconda3/envs/paddle/bin/nvcc' failed with exit code 1
2025-06-12 20:30:51,602 - ERROR - centerpoint_postprocess builded fail!
2025-06-12 20:30:51,602 - ERROR - centerpoint_postprocess builded fail!
Traceback (most recent call last):
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/ops/init.py", line 168, in _load_module
self.module = importlib.import_module(self.modulename)
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1014, in _gcd_import
File "", line 991, in _find_and_load
File "", line 973, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'centerpoint_postprocess'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/utils/cpp_extension/extension_utils.py", line 1152, in run_cmd
return subprocess.check_call(command, shell=True, stdout=DEVNULL)
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/subprocess.py", line 364, in check_call
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command 'cd /home/lib245/.cache/paddle_extensions && /home/lib245/anaconda3/envs/paddle/bin/python centerpoint_postprocess_setup.py build' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "tools/evaluate.py", line 115, in
main(args)
File "tools/evaluate.py", line 110, in main
trainer.evaluate()
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/apis/trainer.py", line 638, in evaluate
result = validation_step(self.model, sample)
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/apis/pipeline.py", line 122, in validation_step
outputs = model(sample)
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 948, in call
return self.forward(*inputs, **kwargs)
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/models/base/base_model.py", line 72, in forward
return self.test_forward(samples, *args, **kwargs)
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/models/detection/centerpoint/centerpoint.py", line 163, in test_forward
preds = self.bbox_head.predict_by_custom_op(samples, preds,
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/site-packages/decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/base.py", line 375, in _decorate_function
return func(*args, **kwargs)
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/models/detection/centerpoint/center_head.py", line 320, in predict_by_custom_op
bboxes, scores, labels = centerpoint_postprocess.centerpoint_postprocess(
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/ops/init.py", line 186, in getattr
module = self._load_module()
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/ops/init.py", line 172, in _load_module
self.module = self.jit_build()
File "/media/lib245/新加卷1/gjk/Paddle3D/paddle3d/ops/init.py", line 159, in jit_build
return paddle_jit_load(
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/utils/cpp_extension/cpp_extension.py", line 944, in load
_jit_compile(file_path, verbose)
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/utils/cpp_extension/extension_utils.py", line 1113, in _jit_compile
run_cmd(compile_cmd, verbose)
File "/home/lib245/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/utils/cpp_extension/extension_utils.py", line 1155, in run_cmd
raise RuntimeError("Failed to run command: {}, errors: {}".format(
RuntimeError: Failed to run command: , errors: Command 'cd /home/lib245/.cache/paddle_extensions && /home/lib245/anaconda3/envs/paddle/bin/python centerpoint_postprocess_setup.py build' returned non-zero exit status 1.

信息显示 auto label_per_task =
paddle::experimental::argmax(sigmoid_hm_per_task, 1, true, false);这个函数参数数量少了，这个问题怎么处理